© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10981
    Prev
    Next
    INDEX
    Explanations

    technical and programming terminology related to user-generated content and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    file paths and directory structures.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Décembre
    -0.63
     Вас
    -0.59
     clearColor
    -0.58
    IAm
    -0.54
     Grecs
    -0.54
     Vám
    -0.54
     Français
    -0.54
     Вам
    -0.53
     Cię
    -0.53
     Messieurs
    -0.53
    POSITIVE LOGITS
     argint
    0.65
     manguera
    0.61
     dignidad
    0.60
     explotación
    0.60
     fisuras
    0.59
     rodillas
    0.59
     rodilla
    0.57
     telefónica
    0.57
    bibfield
    0.57
     москве
    0.57
    Activations Density 4.115%

    No Known Activations